---
title: "Copy-Paste Language Models — GEORecall"
description: "arXiv:2610.19247v1 Announce Type: new Abstract: Transformers are intuitively considered to be efficient at copying from their inputs. We actually show that the…"
	canonical: "https://georecall.ai/spin/copy-paste-language-models"
html: "https://georecall.ai/spin/copy-paste-language-models"
json: "https://georecall.ai/spin/copy-paste-language-models.json"
markdown: "https://georecall.ai/spin/copy-paste-language-models.md"
keywords: ["narrative intelligence", "SpinGraph", "AI recall"]
date: "2026-10-15T04:00:00+00:00"
modified: "2026-10-15T06:02:54.020505+00:00"
json_ld: |
  {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://georecall.ai/#organization","name":"GEORecall","url":"https://georecall.ai/","description":"Know the moment AI knows your story. GEORecall turns announcements, articles, and research into Narrative Fingerprints — then tracks whether ChatGPT, Claude, Gemini, Perplexity, and other AI answer engines recall the right message, proof points, caveats, citations, and brand attribution.","logo":{"@type":"ImageObject","url":"https://georecall.ai/images/logo.png"},"sameAs":[]},{"@type":"NewsArticle","@id":"https://georecall.ai/spin/copy-paste-language-models#article","headline":"Copy-Paste Language Models","description":"arXiv:2610.19247v1 Announce Type: new Abstract: Transformers are intuitively considered to be efficient at copying from their inputs. We actually show that the…","datePublished":"2026-10-15T04:00:00+00:00","dateModified":"2026-10-15T06:02:54.020505+00:00","url":"https://georecall.ai/spin/copy-paste-language-models","mainEntityOfPage":{"@type":"WebPage","@id":"https://georecall.ai/spin/copy-paste-language-models"},"isAccessibleForFree":true,"inLanguage":"en-US","articleSection":"research","author":{"@type":"Organization","name":"arXiv Computation and Language","url":"https://export.arxiv.org/rss/cs.CL"},"publisher":{"@id":"https://georecall.ai/#organization"},"citation":"https://arxiv.org/abs/2610.19247","about":[],"mentions":[{"@type":"Organization","name":"arXiv Computation and Language"}]},{"@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"GEORecall","item":"https://georecall.ai/"},{"@type":"ListItem","position":2,"name":"Copy-Paste Language Models","item":"https://georecall.ai/spin/copy-paste-language-models"}]}]}
---

# Copy-Paste Language Models

**Source:** Unknown  
**Published:** October 15, 2026  
**Original:** https://arxiv.org/abs/2610.19247  

## On this page

- [Overview](#overview)

<a id="overview"></a>

## Overview

arXiv:2610.19247v1 Announce Type: new Abstract: Transformers are intuitively considered to be efficient at copying from their inputs. We actually show that the ability of LLMs to copy in context can be improved through explicit modeling. We propose Copy-Paste Language Models (CPLMs), which add a lightweight Copy-Paste head to the conventional language modeling (LM) head. CPLMs improve training efficiency, downstream performance, and offer new operating points in long-context and retrieval setups

---
*HTML version: https://georecall.ai/spin/copy-paste-language-models*